Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7312
    Prev
    Next
    INDEX
    Explanations

    Java repository-related terms and interfaces, particularly those associated with Spring Data JPA

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Implementing specific "interface" or "JpaRepository"

    np_acts-logits-general · gemini-2.0-flash

    implementing interfaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    حوالہ
    -0.61
    PageModule
    -0.60
    ServiceImpl
    -0.55
    ()));
    
    -0.52
    ())))
    -0.52
    ()]
    
    -0.48
    zelf
    -0.47
    oski
    -0.47
    AndEndTag
    -0.46
    llum
    -0.46
    POSITIVE LOGITS
     interface
    1.45
    interface
    1.23
     interfaces
    1.21
     Interface
    1.18
    Interface
    1.10
     INTERFACE
    1.06
    接口
    1.02
     interfacial
    1.00
     интерфей
    0.97
     Interfaces
    0.93
    Activations Density 0.128%

    No Known Activations